Ambient intelligence assistant for running sports based on k-NN classifiers

Outdoor sport practitioners can improve greatly their results if they train at the right intensity. Nevertheless, in common training systems the athlete's performance is used for evaluation at the end of the exercises, and the sensed data is incomplete because only human biometrics are analyzed. These systems do not consider environmental conditions, which may have direct influence on athlete's performance during training. In this paper, we present the system architecture and implementation of an ambient intelligence assistant for runners. Our system is composed of a Wireless Sensor Network (WSN) deployed over a cross-country running circuit, and by mobile elements carried by the users, which monitor their heart rate (HR). The goal is to select, for a given user, suitable tracks where the heart rate will be in the selected HR range. The decision-taking process is based on k-NN classification and has achieved a success classification ratio of 70%.